Space-time combination based dynamic scene stereo video matching method

Abstract

The invention discloses a space-time combination based dynamic scene stereo video matching method. According to the method, the affine transformation motion of continuous video frames is modeled, a time domain relation among the continuous video frames is created, and a parallax value is selectively optimized by utilizing the geometric correlation between a left view and a right view according to the smoothness constraint for the parallax change of the time domain overlapped segmentation blocks among the continuous video frames on the basis of color segmentation, so that mismatching and parallax jumping phenomena caused by instability of color segmentation blocks in the traditional stereo video matching process are avoided, and a finally-obtained parallax video is more accurate and stable on a timer axis. The space-time combination based dynamic scene stereo video matching method can be used for effectively reducing the jumping phenomenon of the parallax video, well correcting the dismatching introduced to color segmentation and obtaining a more accurate parallax video result.

Description

technical field [0001] The invention relates to a method for matching stereoscopic video to obtain a disparity map video, specifically, to a method for correcting the spatial stereoscopic matching result by using the time domain constraint between continuous video frames of stereoscopic video, thereby improving the stereoscopic A measure of the accuracy of video matching results. Background technique [0002] Obtaining disparity information through stereo matching and then performing 3D reconstruction has always been a hot spot and difficulty in computer vision research. With the rise of 3DTV, the obtained disparity map can not only be used in traditional fields such as 3D modeling and robot navigation, but also widely used in many fields such as stereoscopic video coding and viewpoint synthesis. There are many scholars working on improving the accuracy and efficiency of stereo matching. [0003] Traditional stereo matching methods generally take binocular stereo images as...

AI Technical Summary

Problems solved by technology

However, due to the difficulty of stereo matching and the changes of lighting, noise, motion, texture, occlusion and many other factors in the video, the parallax results are often not stable, which is manifested as the wrong match in the parallax video and the time axis. The phenomenon of parallax jump

The consequences of applying these disparity results with mismatches can sometimes be severe, such as providing incorrect obstacle information to a moving robot, or potentially noticeable artifacts in stereoscopic video rendering, etc.

Images